[PowerPC] Follow-up to r318436 to get the missed CSE opportunities

The last of the three patches that https://reviews.llvm.org/D40348 was
broken up into.
Canonicalize the materialization of constants so that they are more likely
to be CSE'd regardless of the bit-width of the use. If a constant can be
materialized using PPC::LI, materialize it the same way always.
For example:
  li 4, -1
  li 4, 255
  li 4, 65535
are equivalent if the uses only use the low byte. Canonicalize it to the
first form.

Differential Revision: https://reviews.llvm.org/D40348

llvm-svn: 320473

llvm/lib/Target/PowerPC/PPCISelDAGToDAG.cpp

@@ -786,8 +786,10 @@ static SDNode *selectI64ImmDirect(SelectionDAG *CurDAG, const SDLoc &dl,
 
   // Simple value.
   if (isInt<16>(Imm)) {
+    uint64_t SextImm = SignExtend64(Lo, 16);
+    SDValue SDImm = CurDAG->getTargetConstant(SextImm, dl, MVT::i64);
     // Just the Lo bits.
-    Result = CurDAG->getMachineNode(PPC::LI8, dl, MVT::i64, getI32Imm(Lo));
+    Result = CurDAG->getMachineNode(PPC::LI8, dl, MVT::i64, SDImm);
   } else if (Lo) {
     // Handle the Hi bits.
     unsigned OpC = Hi ? PPC::LIS8 : PPC::LI8;
@@ -892,12 +894,74 @@ static SDNode *selectI64Imm(SelectionDAG *CurDAG, const SDLoc &dl,
                                 getI32Imm(64 - RMin), getI32Imm(MaskEnd));
 }
 
+static unsigned allUsesTruncate(SelectionDAG *CurDAG, SDNode *N) {
+  unsigned MaxTruncation = 0;
+  // Cannot use range-based for loop here as we need the actual use (i.e. we
+  // need the operand number corresponding to the use). A range-based for
+  // will unbox the use and provide an SDNode*.
+  for (SDNode::use_iterator Use = N->use_begin(), UseEnd = N->use_end();
+       Use != UseEnd; ++Use) {
+    unsigned Opc =
+      Use->isMachineOpcode() ? Use->getMachineOpcode() : Use->getOpcode();
+    switch (Opc) {
+    default: return 0;
+    case ISD::TRUNCATE:
+      if (Use->isMachineOpcode())
+        return 0;
+      MaxTruncation =
+        std::max(MaxTruncation, Use->getValueType(0).getSizeInBits());
+      continue;
+    case ISD::STORE: {
+      if (Use->isMachineOpcode())
+        return 0;
+      StoreSDNode *STN = cast<StoreSDNode>(*Use);
+      unsigned MemVTSize = STN->getMemoryVT().getSizeInBits();
+      if (MemVTSize == 64 || Use.getOperandNo() != 0)
+        return 0;
+      MaxTruncation = std::max(MaxTruncation, MemVTSize);
+      continue;
+    }
+    case PPC::STW8:
+    case PPC::STWX8:
+    case PPC::STWU8:
+    case PPC::STWUX8:
+      if (Use.getOperandNo() != 0)
+        return 0;
+      MaxTruncation = std::max(MaxTruncation, 32u);
+      continue;
+    case PPC::STH8:
+    case PPC::STHX8:
+    case PPC::STHU8:
+    case PPC::STHUX8:
+      if (Use.getOperandNo() != 0)
+        return 0;
+      MaxTruncation = std::max(MaxTruncation, 16u);
+      continue;
+    case PPC::STB8:
+    case PPC::STBX8:
+    case PPC::STBU8:
+    case PPC::STBUX8:
+      if (Use.getOperandNo() != 0)
+        return 0;
+      MaxTruncation = std::max(MaxTruncation, 8u);
+      continue;
+    }
+  }
+  return MaxTruncation;
+}
+
 // Select a 64-bit constant.
 static SDNode *selectI64Imm(SelectionDAG *CurDAG, SDNode *N) {
   SDLoc dl(N);
 
   // Get 64 bit value.
   int64_t Imm = cast<ConstantSDNode>(N)->getZExtValue();
+  if (unsigned MinSize = allUsesTruncate(CurDAG, N)) {
+    uint64_t SextImm = SignExtend64(Imm, MinSize);
+    SDValue SDImm = CurDAG->getTargetConstant(SextImm, dl, MVT::i64);
+    if (isInt<16>(SextImm))
+      return CurDAG->getMachineNode(PPC::LI8, dl, MVT::i64, SDImm);
+  }
   return selectI64Imm(CurDAG, dl, Imm);
 }
 

llvm/test/CodeGen/PowerPC/store-constant.ll

@@ -1,5 +1,13 @@
 ; RUN: llc < %s -mtriple=powerpc64-unknown-linux-gnu -mcpu=pwr8 -verify-machineinstrs | FileCheck %s
 
+@CVal = external local_unnamed_addr global i8, align 1
+@SVal = external local_unnamed_addr global i16, align 2
+@IVal = external local_unnamed_addr global i32, align 4
+@LVal = external local_unnamed_addr global i64, align 8
+@USVal = external local_unnamed_addr global i16, align 2
+@arr = external local_unnamed_addr global i64*, align 8
+@arri = external local_unnamed_addr global i32*, align 8
+
 ; Test the same constant can be used by different stores.
 
 %struct.S = type { i64, i8, i16, i32 }
@@ -42,3 +50,142 @@ define void @bar(%struct.S* %p) {
 ; CHECK:       stb 4, 8(3)
 }
 
+; Function Attrs: norecurse nounwind
+define void @setSmallNeg() {
+entry:
+  store i8 -7, i8* @CVal, align 1
+  store i16 -7, i16* @SVal, align 2
+  store i32 -7, i32* @IVal, align 4
+  store i64 -7, i64* @LVal, align 8
+  ret void
+; CHECK-LABEL: setSmallNeg
+; CHECK: li 7, -7
+; CHECK-DAG: stb 7,
+; CHECK-DAG: sth 7,
+; CHECK-DAG: stw 7,
+; CHECK-DAG: std 7,
+}
+
+; Function Attrs: norecurse nounwind
+define void @setSmallPos() {
+entry:
+  store i8 8, i8* @CVal, align 1
+  store i16 8, i16* @SVal, align 2
+  store i32 8, i32* @IVal, align 4
+  store i64 8, i64* @LVal, align 8
+  ret void
+; CHECK-LABEL: setSmallPos
+; CHECK: li 7, 8
+; CHECK-DAG: stb 7,
+; CHECK-DAG: sth 7,
+; CHECK-DAG: stw 7,
+; CHECK-DAG: std 7,
+}
+
+; Function Attrs: norecurse nounwind
+define void @setMaxNeg() {
+entry:
+  store i16 -32768, i16* @SVal, align 2
+  store i32 -32768, i32* @IVal, align 4
+  store i64 -32768, i64* @LVal, align 8
+  ret void
+; CHECK-LABEL: setMaxNeg
+; CHECK: li 6, -32768
+; CHECK-DAG: sth 6,
+; CHECK-DAG: stw 6,
+; CHECK-DAG: std 6,
+}
+
+; Function Attrs: norecurse nounwind
+define void @setMaxPos() {
+entry:
+  store i16 32767, i16* @SVal, align 2
+  store i32 32767, i32* @IVal, align 4
+  store i64 32767, i64* @LVal, align 8
+  ret void
+; CHECK-LABEL: setMaxPos
+; CHECK: li 6, 32767
+; CHECK-DAG: sth 6,
+; CHECK-DAG: stw 6,
+; CHECK-DAG: std 6,
+}
+
+; Function Attrs: norecurse nounwind
+define void @setExcessiveNeg() {
+entry:
+  store i32 -32769, i32* @IVal, align 4
+  store i64 -32769, i64* @LVal, align 8
+  ret void
+; CHECK-LABEL: setExcessiveNeg
+; CHECK: lis 5, -1
+; CHECK: ori 5, 5, 32767
+; CHECK-DAG: stw 5,
+; CHECK-DAG: std 5,
+}
+
+; Function Attrs: norecurse nounwind
+define void @setExcessivePos() {
+entry:
+  store i16 -32768, i16* @USVal, align 2
+  store i32 32768, i32* @IVal, align 4
+  store i64 32768, i64* @LVal, align 8
+  ret void
+; CHECK-LABEL: setExcessivePos
+; CHECK: li 6, 0
+; CHECK: ori 6, 6, 32768
+; CHECK-DAG: sth 6,
+; CHECK-DAG: stw 6,
+; CHECK-DAG: std 6,
+}
+
+define void @SetArr(i32 signext %Len) {
+entry:
+  %cmp7 = icmp sgt i32 %Len, 0
+  br i1 %cmp7, label %for.body.lr.ph, label %for.cond.cleanup
+
+for.body.lr.ph:                                   ; preds = %entry
+  %0 = load i64*, i64** @arr, align 8
+  %1 = load i32*, i32** @arri, align 8
+  %wide.trip.count = zext i32 %Len to i64
+  br label %for.body
+
+for.cond.cleanup:                                 ; preds = %for.body, %entry
+  ret void
+
+for.body:                                         ; preds = %for.body, %for.body.lr.ph
+  %indvars.iv = phi i64 [ 0, %for.body.lr.ph ], [ %indvars.iv.next, %for.body ]
+  %arrayidx = getelementptr inbounds i64, i64* %0, i64 %indvars.iv
+  store i64 -7, i64* %arrayidx, align 8
+  %arrayidx2 = getelementptr inbounds i32, i32* %1, i64 %indvars.iv
+  store i32 -7, i32* %arrayidx2, align 4
+  %indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
+  %exitcond = icmp eq i64 %indvars.iv.next, %wide.trip.count
+  br i1 %exitcond, label %for.cond.cleanup, label %for.body
+; CHECK-LABEL: SetArr
+; CHECK: li 5, -7
+; CHECK: stdu 5, 8(3)
+; CHECK: stwu 5, 4(4)
+}
+
+define void @setSameValDiffSizeCI() {
+entry:
+  store i32 255, i32* @IVal, align 4
+  store i8 -1, i8* @CVal, align 1
+  ret void
+; CHECK-LABEL: setSameValDiffSizeCI
+; CHECK: li 5, 255
+; CHECK-DAG: stb 5,
+; CHECK-DAG: stw 5,
+}
+
+define void @setSameValDiffSizeSI() {
+entry:
+  store i32 65535, i32* @IVal, align 4
+  store i16 -1, i16* @SVal, align 2
+  ret void
+; CHECK-LABEL: setSameValDiffSizeSI
+; CHECK: li 5, 0
+; CHECK: ori 5, 5, 65535
+; CHECK-DAG: sth 5,
+; CHECK-DAG: stw 5,
+}

llvm/test/CodeGen/PowerPC/testComparesigeuc.ll

@@ -106,7 +106,7 @@ entry:
   store i8 %conv3, i8* @glob
   ret void
 ; CHECK-LABEL: @test_igeuc_sext_z_store
-; CHECK: li [[REG1:r[0-9]+]], 255
+; CHECK: li [[REG1:r[0-9]+]], -1
 ; CHECK: stb [[REG1]]
 ; CHECK: blr
 }

llvm/test/CodeGen/PowerPC/testComparesigeus.ll

@@ -105,9 +105,8 @@ entry:
   store i16 %conv3, i16* @glob
   ret void
 ; CHECK-LABEL: @test_igeus_sext_z_store
-; CHECK: li [[REG1:r[0-9]+]], 0
+; CHECK: li [[REG1:r[0-9]+]], -1
-; CHECK: ori [[REG2:r[0-9]+]], [[REG1]], 65535
+; CHECK: sth [[REG1]]
-; CHECK: sth [[REG2]]
 ; CHECK: blr
 }
 

llvm/test/CodeGen/PowerPC/testComparesllgeuc.ll

@@ -105,7 +105,7 @@ entry:
   store i8 %conv1, i8* @glob
   ret void
 ; CHECK-LABEL: @test_llgeuc_sext_z_store
-; CHECK: li [[REG1:r[0-9]+]], 255
+; CHECK: li [[REG1:r[0-9]+]], -1
 ; CHECK: stb [[REG1]]
 ; CHECK: blr
 }

llvm/test/CodeGen/PowerPC/testComparesllgeus.ll

@@ -105,9 +105,8 @@ entry:
   store i16 %conv1, i16* @glob
   ret void
 ; CHECK-LABEL: @test_llgeus_sext_z_store
-; CHECK: li [[REG1:r[0-9]+]], 0
+; CHECK: li [[REG1:r[0-9]+]], -1
-; CHECK: ori [[REG2:r[0-9]+]], [[REG1]], 65535
+; CHECK: sth [[REG1]]
-; CHECK: sth [[REG2]]
 ; CHECK: blr  
 }